A guide for writing a GitHub pull-request description from the changes on the current branch. It explains the problem, design decisions, resulting behavior, and relevant context for reviewers.

Use it to draft a PR title and summary, explain rationale and implementation boundaries, incorporate linked issue or design information, and prepare reviewer context against a chosen base branch.

It turns a code diff into a clear explanation of why the changes were made, rather than just listing modified files. It also helps preserve important decisions and unchanged behavior.

gh-pr — Skill for Claude Code and Codex by Unique-Divine

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Unique-Divine/jiyuu --skill gh-pr

Clone the repo

git clone --depth 1 https://github.com/Unique-Divine/jiyuu

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/unique-divine/jiyuu/gh-pr.svg)](https://agentmods.dev/skills/unique-divine/jiyuu/gh-pr)

Your own site

<a href="https://agentmods.dev/skills/unique-divine/jiyuu/gh-pr"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/gh-pr.svg" alt="Measured on agentmods" height="20"></a>

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,193 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00063	$0.01193
Opus 5	$0.00032	$0.00596
Sonnet 5	$0.00013	$0.00239
Haiku 4.5	$0.00006	$0.00119

Measured 8d ago against content hash fd8804af39d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gh-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

ai-skills/gh-pr/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GH PR

Purpose

Create a clear, logical pull request description for the current branch diff against a base branch. A good PR body explains the problem, the decisions that shape the implementation, and the resulting behavior—not merely the changed files.

Instructions

When using this skill:

Determine the comparison branch first:
- Use the branch the user specifies when they name one.
- Otherwise, default to main.
- If the correct base branch is unclear, ask the user before drafting the pull request description.
- If the repo clearly uses another default integration branch, such as dev, use that instead of assuming main.
Read any linked issue, epic, journal, design, or acceptance criteria before drafting. Treat agreed decisions and accounting/event semantics in those documents as source material for the body.
Write a pull request description that explains the rationale behind the changes, not just the file-by-file edits. State what was broken or incomplete, why the chosen boundary or data contract is correct, and which existing semantics intentionally remain unchanged.
Put reviewer context in this order: the PR title and synopsis, ## Rationale, ## Key Changes, then any additional behavior-oriented sections. Keep Rationale and Key Changes unnumbered. Number only the additional topic headings as ## 1 - ..., ## 2 - ..., and so forth. The numbering improves scanning across distinct topics; it does not imply implementation order or runtime sequence.
For changes with non-obvious behavior, cross-system effects, accounting, migrations, or several related fixes, use the additional sections to explain the relevant logic. Name them for the subject—for example ## 1 - Partial-close behavior, ## 2 - Borrowing settlement, or ## 3 - Historical compatibility—rather than using implementation-oriented headings.
For migrations, accounting changes, data-contract cutovers, or asynchronous authority/fallback behavior, lead the relevant additional section with a compact ASCII flow or field map. Use prose afterward only for the rationale the flow cannot convey. Do not use Mermaid.
Do not add a dedicated Validation, Testing, or similarly named section, and do not enumerate routine test, lint, build, formatting, or check runs. Mention test strategy or coverage only when it materially changes or creates a reviewer-relevant risk; place that context in the most relevant behavior-oriented section.
Keep the writing concise and non-repetitive, but do not omit the reasoning that a reviewer needs to validate the design.
Save the final output to a markdown file named gh-pr.md.

Read the full file on GitHub · 123 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 123 lines · 63 tokens per session scan A fd8804af39d7

Subscribe to this mod's changes

gh-pr is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 1,193 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Git and workflow Go ai-context algorithms anki-cards coverage-report go

vhs-e2e-gif

Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit. Use when asked to record an e2e run, demo a fix on a PR, attach a GIF or screen recording to a pull request, show a test passing visually, or produce a terminal…

dimetron/pi-go · 106 tokens

skill-creator

Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory.

agenvoy/Agenvoy · 58 tokens

code-guidelines-go

Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…

dimetron/pi-go · 124 tokens

gh-pr